- Mountain View, Ca
Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Lowest Common Denominator IO. Everything is a list of dictionaries!
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step
Simplifying reinforcement learning for complex game environments
Triton is a dynamic binary analysis library. Build your own program analysis tools, automate your reverse engineering, perform software verification or just emulate code.
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
A Native-PyTorch Library for LLM Fine-tuning
Machine Learning Engineering Open Book
Training LLMs with QLoRA + FSDP
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Annotated version of the Mamba paper
Constrained Decoding for LLMs against JSON Schema
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Solve puzzles. Improve your pytorch.
moonbucks / nanoGPT
Forked from karpathy/nanoGPTThe simplest, fastest repository for training/finetuning medium-sized GPTs.
Automatically split your PyTorch models on multiple GPUs for training & inference
This Repository contains some examples of source-to-source transformations applied with LLVM's LibTooling and RecursiveASTVisitor
ChrisHayduk / qlora-multi-gpu
Forked from artidoro/qloraQLoRA with Enhanced Multi GPU Support
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Easily process files one line at a time with Python
A fast inference library for running LLMs locally on modern consumer-class GPUs
QLoRA: Efficient Finetuning of Quantized LLMs
Jupyter notebooks for tutorial on the Z3 SMT solver